Commit History
doc: add reference
fd1dead
disable queue in dalle-mini demo (#188)
604225f
unverified
AK391
commited on
feat(app): migrate demo to Gradio by @AK391 (#179)
616cf8e
unverified
fix(colab): use correct param name for CLIP
badd15c
feat(colab): use full precision for clip & vqgan
8845d77
feat(colab): require less memory
5f16fb0
fix(train): overwrite dropout only when specified
89bc9d4
feat: allow eval only
65bb95f
feat(colab): update mini checkpoint
a4d2af8
feat(train): allow editing dropout during training
80d791a
feat(colab): require less resources
b6f5026
docs: add dalle flow project to readme (#182)
5537306
unverified
feat(colab): change defaults
3de3769
feat(colab): handle dalle-mega
024f8f5
feat: support LR offset (#174)
c3e93df
unverified
feat: update shampoo
79a3849
feat(train): allow nesterov momentum
d08bf8d
feat: allow weight decay
acc1a4a
Merge pull request #173 from borisdayma/fix-run_reference
b4bb5b9
unverified
Pedro Cuenca
commited on
Remove model version for now.
d9bb466
Pedro Cuenca
commited on
feat: release action
4381fec
Style. Sorry, forgot to run `black`.
b71e7a4
Pedro Cuenca
commited on
Remove reference to previous training run.
85d174c
Pedro Cuenca
commited on
feat: use default from_pretrained function
4ac66e4
style: reformat
dca3ada
feat(train): use new HF _do_init api
6b84155
fix: model compatible with do_init
f3a8cbb
fix: apply learning rate offset only when requested
c6263f3
Merge pull request #171 from borisdayma/reduced-requests
209ade7
unverified
Pedro Cuenca
commited on
feat(train): arg to offset lr for resumed runs
89b4c45
Half the number of requests.
d6e9f87
Pedro Cuenca
commited on
feat(demo): use vaild model
23c1ef6
feat(mega): switch to gelu
cdefdd0
feat: layernorm > rmsnorm in long runs
0f2cf98
fix: use correctly cache during inference + allow unscan (#170)
42968cf
unverified
fix: allow non-scanned models (#168)
8ae9176
unverified
feat(demo): do not log search
3500e67
feat: vmap optimizer (#166)
b993d27
unverified
feat(demo): use fixed commit
2f1e5d9
doc: reference dalle playground
648305a
feat: scan layers + gradient checkpointing (#161)
07a6f9a
unverified
Merge pull request #162 from borisdayma/demo-improvements
0199604
unverified
Pedro Cuenca
commited on
Merge branch 'main' of https://github.com/borisdayma/dalle-mini into main
bcd360f
Style: run isort.
58b9afd
Pedro Cuenca
commited on
Style: run black.
2d6dbdd
Pedro Cuenca
commited on
Display info about model and run, below predictions.
13caa60
Pedro Cuenca
commited on
Update year: 2021-2022
f58c732
Pedro Cuenca
commited on
Log dates
687a914
Pedro Cuenca
commited on
Move client api to backend.py
63679e9
Pedro Cuenca
commited on